Artificial intelligence · CSET301
Artificial Intelligence and Machine Learning
Explore supervised and unsupervised learning, build and evaluate models, and apply AI and machine learning to practical problems.
Learning outcomes
In plain language, this course develops the following abilities.
- Explain supervised and unsupervised machine learning approaches.
- Build and evaluate models generated from data.
- Implement AI and machine learning systems for real-life problems.
Syllabus overview
Learning systems and regression
Learning paradigms, linear and logistic regression, gradient descent and evaluation metrics.
Trees and ensembles
Decision trees, overfitting, cross-validation, random forests, boosting and feature engineering.
Neural and Bayesian learning
Neural networks, backpropagation, optimisation, regularisation and Bayesian learning.
Related courses
These links suggest related topics; they are not formal prerequisite requirements.
Source and scope
Summarised from the official 2023–2027 booklet, PDF page 76 and its continuation. Course facts follow the curriculum listing. This page is part of a student academic project.